1 citations · 1 across the 9 of their papers we have counts for
5 papers · 1 filter
Late Attention Layers Alone Can Copy Entity Tokens, but Not Without Attending to Their Context
Muyu He, Yuchen Liu, Ran Tao +1
Large language models (LLMs) reliably perform entity copying, in which a model copies tokens referring to an entity, termed entity tokens, from the prompt into its output to answer…
MADE: Beyond Scoring via a Multilingual Agentic Diagnosing Engine for Fine-Grained Evaluation Insights
Yilun Liu, Miao Zhang, Shimin Tao +9
Multilingual and multicultural benchmarks now cover dozens of languages and model families, but the resulting score landscapes remain metric-rich and insight-poor, necessitating fi…
The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models
Yilun Liu, Chunguang Zhao, Mengyao Piao +14
Evaluating the multilingual and multicultural capabilities of Large Language Models (LLMs) is essential for their global utility. However, current benchmarks face three critical li…
C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignment
Pufan Zeng, Yilun Liu, Mingchen Dai +12
Achieving cultural alignment in Large Language Models (LLMs) increasingly depends on synthetic data generation. For such synthesis, the most vital initial step is seed curation; ho…
Think in Latent Thoughts: A New Paradigm for Gloss-Free Sign Language Translation
Yiyang Jiang, Li Zhang, Xiao-Yong Wei +1
Many SLT systems quietly assume that brief chunks of signing map directly to spoken-language words. That assumption breaks down because signers often create meaning on the fly usin…